Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 19274
    Prev
    Next
    INDEX
    Explanations

    words ending with 'uf' followed by a number, indicating a player's name or similar reference in a sports-related context

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific name or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ashore
    -0.71
     Carmen
    -0.68
     Siren
    -0.67
     Bender
    -0.61
     tant
    -0.60
     Reign
    -0.59
     Rift
    -0.59
     Carroll
    -0.58
     Sapphire
    -0.58
    PUT
    -0.58
    POSITIVE LOGITS
    uf
    1.01
    ortun
    0.94
    eatures
    0.90
    req
    0.88
    lections
    0.86
    igi
    0.85
    ornia
    0.83
    ranch
    0.83
    uitous
    0.82
    edd
    0.82
    Activations Density 0.008%

    No Known Activations